© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7704
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographic locations, particularly cities and countries

    oai_token-act-pair · gpt-3.5-turbo

    names of North African countries and cities, particularly Tunisia and Algeria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peat
    -0.90
    gling
    -0.86
    rint
    -0.83
    ãĥīãĥ©
    -0.83
    tsky
    -0.82
    usable
    -0.82
    baugh
    -0.81
    croft
    -0.81
    respond
    -0.80
    owder
    -0.79
    POSITIVE LOGITS
    ienne
    0.83
     Tanz
    0.79
    iana
    0.74
     Brah
    0.74
     Mas
    0.67
    oler
    0.67
    ique
    0.67
     Mohamed
    0.66
     Kou
    0.66
    essa
    0.65
    Activations Density 0.091%

    No Known Activations